© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32889
    Prev
    Next
    INDEX
    Explanations

    features, configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تساوي
    0.45
    imar
    0.43
     يساوي
    0.42
     ندارد
    0.41
    ట
    0.40
    gathering
    0.40
     ***",
    0.39
     دارد
    0.39
    集
    0.39
    बा
    0.38
    POSITIVE LOGITS
     available
    0.43
    available
    0.41
     ODM
    0.40
     Available
    0.38
     બંધ
    0.37
     unavailable
    0.37
     品
    0.34
    accessible
    0.34
     Els
    0.33
     Orientation
    0.33
    Activations Density 0.010%

    No Known Activations